SKILLEMALL.ai
RU Sign in

CF openclaw

Télécharge automatiquement la dernière vidéo (ou les N dernières) d'un compte TikTok public via yt-dlp. Utilise ce skill dès que l'utilisateur mentionne TikTok, un @username TikTok, "télécharger une vidéo TikTok", "récupérer le dernier post TikTok", "dernière vidéo d'un compte", "scraper TikTok", ou toute demande de download/extraction de contenu depuis TikTok. Fonctionne aussi pour récupérer uniquement les métadonnées (titre, hashtags, date, stats) sans téléchargement. À utiliser aussi quand l'utilisateur demande "télécharger un compte TikTok", "archiver des vidéos TikTok", ou veut automatiser la récupération de contenu TikTok.

Not recommendedcritical or high security findings
modbender/skill-library-mcp Agent Skills author: modbender MIT 5 files body ≈ 1 410 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Télécharge automatiquement la dernière vidéo (ou les N dernières) d'un compte TikTok public via yt-dlp.

As a process F 28/100 · Will not run — References files that are not bundled: references/metadata.md

ProcedureMarketingtype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
C
62/100
safety, quality, tests
Safety 60%
59
Quality 40%
67
Run on models
none yet
Process rating
F
28/100
Will not run
References files that are not bundled: references/metadata.md
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Exfiltration
If you install

The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

How to improve

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
  2. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  3. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 3

  • high Exfiltration intent-browser-credential-store advanced.md:29
    Accesses a browser credential / cookie store
    yt-dlp --cookies-from-browser chrome URL
  • high Exfiltration intent-browser-credential-store advanced.md:35
    Accesses a browser credential / cookie store
    yt-dlp --cookies-from-browser edge URL
Medium and low: 1
  • medium Exfiltration intent-browser-credential-store SKILL.md:124
    Accesses a browser credential / cookie store (documentation table row)
    | `Private account` | Compte privé | Utiliser `--cookies-from-browser chrome` si connecté |
    table

Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning missing-ref reference to a missing file: references/metadata.md

Process rating: all ten parameters 28/100

Will not run. References files that are not bundled: references/metadata.md
  • 0Tools and files. 1 referenced file(s) missing: references/metadata.md
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 1 mutating operations with no state check
  • 40Consistency. Frontmatter name (openclaw) differs from the folder (download-video-tiktok)
  • 100Steps. 33 steps
  • 100Execution cost. Instruction body is 1410 tokens

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • -4Absolute local paths (C:\Users, /home/…): not portable
  • +1No license
  • +2Single-language instructions
  • +5Description quotes 6 example trigger phrases
  • +3Description length 636: enough signal without eating the budget
  • +4Structure: 14 headings
  • +3Step-by-step instructions: 33 items
  • +4Has examples (7 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 67.